You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/release-notes/known-issues.md
+20Lines changed: 20 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,8 +8,28 @@ mapped_pages:
8
8
9
9
Known issues are significant defects or limitations that may impact your implementation. These issues are actively being worked on and will be addressed in a future release. Review the Elasticsearch known issues to help you make informed decisions, such as upgrading to a new version.
10
10
11
+
## 9.1.1 [elasticsearch-9.1.1-known-issues]
12
+
13
+
* An [optimization](https://github.com/elastic/elasticsearch/pull/125403) introduced in 9.1.0 contains a [bug](https://github.com/elastic/elasticsearch/pull/132597) that causes merges to fail for shrunk TSDB and LogsDB indices.
14
+
15
+
Possible *temporary* workarounds include:
16
+
* Configure the ILM policy to not perform force merges after shrinking TSDB or LogsDB indices.
17
+
* Add `-Dorg.elasticsearch.index.codec.tsdb.es819.ES819TSDBDocValuesConsumer.enableOptimizedMerge=false` as a Java system property to all data nodes in the cluster and perform a rolling restart.
18
+
**Important:* Remove this property when upgrading to the fixed version to re-enable merge optimization. Otherwise, merges will be slower.
19
+
20
+
The bug is addressed in version 9.1.2.
21
+
11
22
## 9.1.0 [elasticsearch-9.1.0-known-issues]
12
23
24
+
* An [optimization](https://github.com/elastic/elasticsearch/pull/125403) introduced in 9.1.0 contains a [bug](https://github.com/elastic/elasticsearch/pull/132597) that causes merges to fail for shrunk TSDB and LogsDB indices.
25
+
26
+
Possible *temporary* workarounds include:
27
+
* Configure the ILM policy to not perform force merges after shrinking TSDB or LogsDB indices.
28
+
* Add `-Dorg.elasticsearch.index.codec.tsdb.es819.ES819TSDBDocValuesConsumer.enableOptimizedMerge=false` as a Java system property to all data nodes in the cluster and perform a rolling restart.
29
+
**Important:* Remove this property when upgrading to the fixed version to re-enable merge optimization. Otherwise, merges will be slower.
30
+
31
+
The bug is addressed in version 9.1.2.
32
+
13
33
* The `-Dvector.rescoring.directio` JVM option is enabled (set to `true`) by default. When used with `bbq_hnsw` type vector indices, this can cause significant search performance degradation; particularly when enough memory is available to hold all vector data. In some cases, kNN search latency can increase by as much as 10x. To mitigate this, set the JVM option `-Dvector.rescoring.directio=false` on all search nodes and restart them. This option can be removed in 9.1.1.
14
34
15
35
**How do I know if my index vector type is `bbq_hnsw`?**
0 commit comments